Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1672 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.7546. Min Act: -0.1700

Data Index: 887246 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.6109. Min Act: -0.1700

Data Index: 1112000 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.6002. Min Act: -0.1700

Data Index: 1287173 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5306. Min Act: -0.1700

Data Index: 787168 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5419. Min Act: -0.1700

Data Index: 829265 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5306. Min Act: -0.1700

Data Index: 856964 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5109. Min Act: -0.1700

Data Index: 1007609 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5242. Min Act: -0.1700

Data Index: 632868 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5016. Min Act: -0.1700

Data Index: 660672 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5041. Min Act: -0.1700

Data Index: 192671 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5059. Min Act: -0.1700

Data Index: 187832 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5155. Min Act: -0.1700

Data Index: 1301672 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5213. Min Act: -0.1700

Data Index: 680414 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5148. Min Act: -0.1700

Data Index: 1170560 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5008. Min Act: -0.1700

Data Index: 1231638 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5056. Min Act: -0.1700

Data Index: 320418 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5073. Min Act: -0.1700

Data Index: 1354537 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4916. Min Act: -0.1700

Data Index: 475818 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4956. Min Act: -0.1700

Data Index: 898369 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4746. Min Act: -0.1700

Data Index: 340738 (C4 (Web Text))

Max Activating Token Index: 20